Efforts are continually underway to make improvements in materials, electronics … TEDANN: Turbine Engine Diagnostic Artificial Neural Network. The American Defense Preparedness … Paper presented at the International Society of Logistics (SOLE) 1999 Symposium, Las Vegas, Nevada, August 30 - September 2, 1999. 1 Gas Turbine Engine Health Monitoring and Prognostics Frank L. Greitzer, Lars J. Kangas, Kristine M. Terrones, Melody A. Maynard, Bary W. Wilson, Ronald A. Pawlowski, Daniel R. Sisk, and Newton B. Brown Pacific …

Real-Time Predictive Analysis Under an Interagency Agreement with the U.S. Army Logistics Integration Agency, Pacific Northwest National Laboratory (PNNL) is developing a prototype diagnostic/prognostic system for the MBT’s AGT1500 turbine engine that uses artificial neural networks to diagnose and predict faults. The operational prototype system is called TEDANN, for Turbine Engine Diagnostics using Artificial Neural Networks (Greitzer et al. 1997; Illi et al. 1994; Kangas et al. 1994). The main tasks of the TEDANN project are to develop prototype data acquisition hardware, to design and implement health monitoring software, and demonstrate the proof-of- concept system. TEDANN will: • Reduce maintenance staff hours • Improve diagnostics • Enhance readiness • Provide for optimized maintenance scheduling TEDANN Seeks to Demonstrate an Enabling Technology for Condition-Based Maintenance and Anticipatory Logistics When fully implemented, TEDANN will diagnose/prognose the engine health using onboard sensors. Artificial neural network (ANN) capable of sensor fusion identify deviations from normal operation. Ultimately, fielding this technology in the MBT fleet will enable diagnostic/ prognostic information to be conveyed via telemetry to command/control and maintenance support so that battle readiness and maintenance needs may be assessed immediately. System Design/Fabrication TEDANN receives input from 48 sensors mounted on the AGT1500 engine. Of these sensors, 32 are factory installed for engine control and basic diagnostics performed by the engine control unit. The other sixteen sensors—retrofitted to the engine using a wiring harness— include seven pressure sensors, six temperature sensors, two chip detectors, a vibration sensor and an inclinometer. Advanced microsensor technology has been exploited in this and related projects (Wilson et al. 1999). The thermodynamic (temperature, pressure, RPM, etc.) sensors are located at strategic points along the gas flow in the engine to provide more detailed thermodynamic picture of the engine’s state. The TEDANN prototype is contained in an enclosure about one foot square and 3 inches high. The sensor signals are conditioned using two printed circuit boards, multiplexed to a data acquisition card, and then analyzed by a Pentium microprocessor. If fully deployed in the field, the TEDANN system would be integrated with other electronic systems onboard the tank.

Download Gas Turbine Engine Health Monitoring and Prognostics.Pdf